liangdabiao/ecom-details-image

一个面向workbuddy / Codex 等agent 的跨境电商和国内电商通用视觉创作 Skill。我精选25个高质量案例，涵盖纯色底产品主图、场景化生活图、平铺图、电商详情图、真实场景等等，全部配完整提示词，都可以利用 GPT-Image-2 API生成最终效果。一键生成电商相关图片！输入产品图片和需求描述，自动生成完整的电商主图、详情页图片、社媒推广图、直播间场景图等全套视觉素材。 与众不同之处是：**Campaign Style Lock** 机制 和 **强推广** 和 **重视转化效果**。

What it solves

This project provides a specialized toolset for e-commerce sellers to automatically generate professional product imagery. It solves the problem of creating consistent, high-conversion visual assets—such as main product photos, Amazon/Shopify detail pages, and social media promotional content—without needing a professional photographer or a complex design workflow.

How it works

The tool operates as a "Skill" for AI assistants like Claude Code or Codex. It uses a combination of 25 predefined scene templates (ranging from white-background studio shots to lifestyle and infographic styles) and a specialized "Campaign Style Lock" mechanism to ensure visual consistency across a set of images.

Users can provide a product photo and a description of their needs. The system then performs a "conversion drive diagnosis" to determine the best visual strategy (visual-driven, pain-point-driven, or emotional-value-driven) and generates a sequence of images. It can either output the prompts for manual use or directly call an OpenAI-compatible image generation API to produce the final assets.

Who it’s for

  • E-commerce entrepreneurs selling on platforms like Amazon, Shopify, or TikTok/Douyin.
  • Digital marketers needing quick, high-quality social media assets for Twitter/X or Instagram.
  • Product managers creating rapid prototypes of product detail pages (PDP).

Highlights

  • Campaign Style Lock: Automatically locks color palettes, lighting, and layout to maintain a consistent brand look across multiple images.
  • 25 Scene Templates: Comprehensive coverage of e-commerce needs, including exploded views, ghost mannequins, and livestreaming backgrounds.
  • Conversion-Driven Design: Analyzes the product's selling point to tailor the image sequence for maximum conversion.
  • Flexible Output: Supports both a prompt-only mode and a direct API-generation mode.
  • Zero Dependency Script: The image generation script is implemented using only the Python standard library.

Related

  • Project
    s2b-dev/smart-second-brain

    The ​​​  ​  ​  …...............

  • Project
    ShiftHackZ/Stable-Diffusion-KMP

    An open-source, cross-platform AI image generation client for Android and iOS that connects to self-hosted Stable Diffusion servers, cloud APIs, and local on-device runtimes.

  • Project
    ModelTC/LightX2V-Qwen-Image-Lightning

    A distilled, faster version of the Qwen‑Image text‑to‑image model (4‑ or 8‑step diffusion) with fp32/bf16/fp8 checkpoints, LoRA adapters, and ready‑to‑use ComfyUI workflows. Provides 12–25× speed‑up with modest quality loss and integrates with Diffusers, ComfyUI, Nunchaku, and Cache‑dit.

  • Project
    FireRedTeam/FireRed-Image-Edit

    A general-purpose image editing model that provides high-fidelity, consistent edits with strong identity preservation and multi-element fusion capabilities.